旧漢字を新漢字に変換するスクリプト

home 　cgi 　ScriptMenu	新旧漢字対照表　　新漢字→旧漢字　　青空文庫の※を漢字に変換　　説明
旧漢字を新漢字に変換するパールスクリプト
まず、パールをインストールして、パスを通しておいてください。
下のテキストボックスを全選択、コピーして、メモ帳などで、ファイル名を kyukanji.pl などとして保存します。拡張子は必ず .pl にしてください。
文字コードは utf-8 です。
変換元となるテキストファイルも utf-8 に変換しておいてください。

plファイルを置いたフォルダの下にworksというフォルダを作って、そこに変換元となるファイルを置いてください。

［例］　C:\data\text\perl に kyukanji.pl を置いて、
　　　　その下層のフォルダ　C:\data\text\perl\works に aozora.txt を置く。

エクスプローラから kyukanji.pl を選んでエンターキーを押すと、works フォルダに kanji_shin_aozora.txt という変換済みのファイルが生成されます。
kyukanji.pl

# 旧漢字を新漢字に変換
# 入力ファイルの文字コードがutf8であることを確認すべし
# 対象ファイルの拡張子は txt または dat
# kanji から始まるファイルは対象から除外
# 出力ファイルは kanji_shin_$file
# 元ファイルが aozora.txt ならば kanji_shin_aozora.txt

# ディレクトリを開く

	$crdr = "./works/";
	opendir(DIR,"$crdr");
	chdir $crdr;

# ファイル名を配列に格納
	@files = readdir(DIR);


# テキストファイルを順次開く
	foreach $file (@files){

		if ($file =~ /^kanji/ ){ next;}
		if ($file =~ /txt$/i || $file =~ /dat$/i){
			open (IN,"$file") || &error ("file not found");
			open(OUT, "> tmp.txt");
			while(<IN>){
				
#				$_ =~ s/櫻/桜/g;
#				$_ =~ s/嶽/岳/g;
#				$_ =~ s/燈/灯/g;
#				$_ =~ s/佛/仏/g;
#				$_ =~ s/萬/万/g;
#				$_ =~ s/龍/竜/g;

				$_ =~ s/罐/缶/g;
				$_ =~ s/亞/亜/g;
				$_ =~ s/惡/悪/g;
				$_ =~ s/壓/圧/g;
				$_ =~ s/圍/囲/g;
				$_ =~ s/醫/医/g;
				$_ =~ s/爲/為/g;
				$_ =~ s/壹/壱/g;
				$_ =~ s/逸/逸/g;
				$_ =~ s/飮/飲/g;
				$_ =~ s/隱/隠/g;
				$_ =~ s/羽/羽/g;
				$_ =~ s/榮/栄/g;
				$_ =~ s/營/営/g;
				$_ =~ s/銳/鋭/g;
				$_ =~ s/衞/衛/g;
				$_ =~ s/益/益/g;
				$_ =~ s/驛/駅/g;
				$_ =~ s/悅/悦/g;
				$_ =~ s/謁/謁/g;
				$_ =~ s/閱/閲/g;
				$_ =~ s/圓/円/g;
				$_ =~ s/鹽/塩/g;
				$_ =~ s/緣/縁/g;
				$_ =~ s/艷/艶/g;
				$_ =~ s/應/応/g;
				$_ =~ s/歐/欧/g;
				$_ =~ s/毆/殴/g;
				$_ =~ s/奧/奥/g;
				$_ =~ s/橫/横/g;
				$_ =~ s/溫/温/g;
				$_ =~ s/穩/穏/g;
				$_ =~ s/假/仮/g;
				$_ =~ s/價/価/g;
				$_ =~ s/禍/禍/g;
				$_ =~ s/畫/画/g;
				$_ =~ s/會/会/g;
				$_ =~ s/悔/悔/g;
				$_ =~ s/海/海/g;
				$_ =~ s/繪/絵/g;
				$_ =~ s/壞/壊/g;
				$_ =~ s/懷/懐/g;
				$_ =~ s/慨/慨/g;
				$_ =~ s/槪/概/g;
				$_ =~ s/擴/拡/g;
				$_ =~ s/殼/殻/g;
				$_ =~ s/覺/覚/g;
				$_ =~ s/學/学/g;
				$_ =~ s/樂/楽/g;
				$_ =~ s/喝/喝/g;
				$_ =~ s/渴/渇/g;
				$_ =~ s/褐/褐/g;
				$_ =~ s/鐮/鎌/g;
				$_ =~ s/卷/巻/g;
				$_ =~ s/陷/陥/g;
				$_ =~ s/閒/間/g;
				$_ =~ s/勸/勧/g;
				$_ =~ s/寬/寛/g;
				$_ =~ s/漢/漢/g;
				$_ =~ s/關/関/g;
				$_ =~ s/歡/歓/g;
				$_ =~ s/館/館/g;
				$_ =~ s/觀/観/g;
				$_ =~ s/顏/顔/g;
				$_ =~ s/巖/巌/g;
				$_ =~ s/氣/気/g;
				$_ =~ s/祈/祈/g;
				$_ =~ s/既/既/g;
				$_ =~ s/旣/既/g;
				$_ =~ s/歸/帰/g;
				$_ =~ s/龜/亀/g;
				$_ =~ s/器/器/g;
				$_ =~ s/僞/偽/g;
				$_ =~ s/戲/戯/g;
				$_ =~ s/犧/犠/g;
				$_ =~ s/卻/却/g;
				$_ =~ s/舊/旧/g;
				$_ =~ s/據/拠/g;
				$_ =~ s/擧/挙/g;
				$_ =~ s/虛/虚/g;
				$_ =~ s/峽/峡/g;
				$_ =~ s/挾/挟/g;
				$_ =~ s/狹/狭/g;
				$_ =~ s/强/強/g;
				$_ =~ s/敎/教/g;
				$_ =~ s/鄕/郷/g;
				$_ =~ s/響/響/g;
				$_ =~ s/堯/尭/g;
				$_ =~ s/曉/暁/g;
				$_ =~ s/勤/勤/g;
				$_ =~ s/謹/謹/g;
				$_ =~ s/區/区/g;
				$_ =~ s/驅/駆/g;
				$_ =~ s/勳/勲/g;
				$_ =~ s/薰/薫/g;
				$_ =~ s/徑/径/g;
				$_ =~ s/莖/茎/g;
				$_ =~ s/契/契/g;
				$_ =~ s/惠/恵/g;
				$_ =~ s/揭/掲/g;
				$_ =~ s/溪/渓/g;
				$_ =~ s/經/経/g;
				$_ =~ s/螢/蛍/g;
				$_ =~ s/輕/軽/g;
				$_ =~ s/繼/継/g;
				$_ =~ s/鷄/鶏/g;
				$_ =~ s/藝/芸/g;
				$_ =~ s/擊/撃/g;
				$_ =~ s/缺/欠/g;
				$_ =~ s/硏/研/g;
				$_ =~ s/縣/県/g;
				$_ =~ s/儉/倹/g;
				$_ =~ s/劍/剣/g;
				$_ =~ s/險/険/g;
				$_ =~ s/圈/圏/g;
				$_ =~ s/檢/検/g;
				$_ =~ s/獻/献/g;
				$_ =~ s/權/権/g;
				$_ =~ s/顯/顕/g;
				$_ =~ s/驗/験/g;
				$_ =~ s/彥/彦/g;
				$_ =~ s/嚴/厳/g;
				$_ =~ s/戶/戸/g;
				$_ =~ s/吳/呉/g;
				$_ =~ s/娛/娯/g;
				$_ =~ s/廣/広/g;
				$_ =~ s/效/効/g;
				$_ =~ s/恆/恒/g;
				$_ =~ s/黃/黄/g;
				$_ =~ s/鑛/鉱/g;
				$_ =~ s/號/号/g;
				$_ =~ s/吿/告/g;
				$_ =~ s/國/国/g;
				$_ =~ s/黑/黒/g;
				$_ =~ s/穀/穀/g;
				$_ =~ s/碎/砕/g;
				$_ =~ s/濟/済/g;
				$_ =~ s/齋/斎/g;
				$_ =~ s/歲/歳/g;
				$_ =~ s/劑/剤/g;
				$_ =~ s/册/冊/g;
				$_ =~ s/殺/殺/g;
				$_ =~ s/雜/雑/g;
				$_ =~ s/參/参/g;
				$_ =~ s/棧/桟/g;
				$_ =~ s/蠶/蚕/g;
				$_ =~ s/慘/惨/g;
				$_ =~ s/產/産/g;
				$_ =~ s/贊/賛/g;
				$_ =~ s/殘/残/g;
				$_ =~ s/絲/糸/g;
				$_ =~ s/祉/祉/g;
				$_ =~ s/視/視/g;
				$_ =~ s/齒/歯/g;
				$_ =~ s/飼/飼/g;
				$_ =~ s/兒/児/g;
				$_ =~ s/辭/辞/g;
				$_ =~ s/濕/湿/g;
				$_ =~ s/實/実/g;
				$_ =~ s/寫/写/g;
				$_ =~ s/社/社/g;
				$_ =~ s/舍/舎/g;
				$_ =~ s/者/者/g;
				$_ =~ s/煮/煮/g;
				$_ =~ s/釋/釈/g;
				$_ =~ s/壽/寿/g;
				$_ =~ s/收/収/g;
				$_ =~ s/臭/臭/g;
				$_ =~ s/從/従/g;
				$_ =~ s/澁/渋/g;
				$_ =~ s/獸/獣/g;
				$_ =~ s/縱/縦/g;
				$_ =~ s/祝/祝/g;
				$_ =~ s/肅/粛/g;
				$_ =~ s/處/処/g;
				$_ =~ s/渚/渚/g;
				$_ =~ s/暑/暑/g;
				$_ =~ s/署/署/g;
				$_ =~ s/緖/緒/g;
				$_ =~ s/諸/諸/g;
				$_ =~ s/敍/叙/g;
				$_ =~ s/尙/尚/g;
				$_ =~ s/將/将/g;
				$_ =~ s/祥/祥/g;
				$_ =~ s/稱/称/g;
				$_ =~ s/涉/渉/g;
				$_ =~ s/燒/焼/g;
				$_ =~ s/證/証/g;
				$_ =~ s/奬/奨/g;
				$_ =~ s/條/条/g;
				$_ =~ s/狀/状/g;
				$_ =~ s/乘/乗/g;
				$_ =~ s/淨/浄/g;
				$_ =~ s/剩/剰/g;
				$_ =~ s/疊/畳/g;
				$_ =~ s/繩/縄/g;
				$_ =~ s/壤/壌/g;
				$_ =~ s/孃/嬢/g;
				$_ =~ s/穰/穣/g;
				$_ =~ s/讓/譲/g;
				$_ =~ s/釀/醸/g;
				$_ =~ s/觸/触/g;
				$_ =~ s/囑/嘱/g;
				$_ =~ s/神/神/g;
				$_ =~ s/晉/晋/g;
				$_ =~ s/眞/真/g;
				$_ =~ s/寢/寝/g;
				$_ =~ s/愼/慎/g;
				$_ =~ s/盡/尽/g;
				$_ =~ s/圖/図/g;
				$_ =~ s/粹/粋/g;
				$_ =~ s/醉/酔/g;
				$_ =~ s/穗/穂/g;
				$_ =~ s/隨/随/g;
				$_ =~ s/髓/髄/g;
				$_ =~ s/樞/枢/g;
				$_ =~ s/數/数/g;
				$_ =~ s/瀨/瀬/g;
				$_ =~ s/聲/声/g;
				$_ =~ s/靑/青/g;
				$_ =~ s/齊/斉/g;
				$_ =~ s/淸/清/g;
				$_ =~ s/晴/晴/g;
				$_ =~ s/靖/靖/g;
				$_ =~ s/精/精/g;
				$_ =~ s/靜/静/g;
				$_ =~ s/稅/税/g;
				$_ =~ s/竊/窃/g;
				$_ =~ s/攝/摂/g;
				$_ =~ s/節/節/g;
				$_ =~ s/說/説/g;
				$_ =~ s/絕/絶/g;
				$_ =~ s/專/専/g;
				$_ =~ s/淺/浅/g;
				$_ =~ s/戰/戦/g;
				$_ =~ s/踐/践/g;
				$_ =~ s/錢/銭/g;
				$_ =~ s/潛/潜/g;
				$_ =~ s/纖/繊/g;
				$_ =~ s/禪/禅/g;
				$_ =~ s/祖/祖/g;
				$_ =~ s/雙/双/g;
				$_ =~ s/壯/壮/g;
				$_ =~ s/爭/争/g;
				$_ =~ s/莊/荘/g;
				$_ =~ s/搜/捜/g;
				$_ =~ s/插/挿/g;
				$_ =~ s/巢/巣/g;
				$_ =~ s/曾/曽/g;
				$_ =~ s/瘦/痩/g;
				$_ =~ s/裝/装/g;
				$_ =~ s/僧/僧/g;
				$_ =~ s/層/層/g;
				$_ =~ s/總/総/g;
				$_ =~ s/聰/聡/g;
				$_ =~ s/騷/騒/g;
				$_ =~ s/增/増/g;
				$_ =~ s/憎/憎/g;
				$_ =~ s/藏/蔵/g;
				$_ =~ s/贈/贈/g;
				$_ =~ s/臟/臓/g;
				$_ =~ s/卽/即/g;
				$_ =~ s/屬/属/g;
				$_ =~ s/續/続/g;
				$_ =~ s/墮/堕/g;
				$_ =~ s/對/対/g;
				$_ =~ s/體/体/g;
				$_ =~ s/帶/帯/g;
				$_ =~ s/滯/滞/g;
				$_ =~ s/臺/台/g;
				$_ =~ s/瀧/滝/g;
				$_ =~ s/擇/択/g;
				$_ =~ s/澤/沢/g;
				$_ =~ s/琢/琢/g;
				$_ =~ s/脫/脱/g;
				$_ =~ s/擔/担/g;
				$_ =~ s/單/単/g;
				$_ =~ s/膽/胆/g;
				$_ =~ s/嘆/嘆/g;
				$_ =~ s/團/団/g;
				$_ =~ s/斷/断/g;
				$_ =~ s/彈/弾/g;
				$_ =~ s/遲/遅/g;
				$_ =~ s/癡/痴/g;
				$_ =~ s/蟲/虫/g;
				$_ =~ s/晝/昼/g;
				$_ =~ s/鑄/鋳/g;
				$_ =~ s/著/著/g;
				$_ =~ s/猪/猪/g;
				$_ =~ s/廳/庁/g;
				$_ =~ s/徵/徴/g;
				$_ =~ s/聽/聴/g;
				$_ =~ s/懲/懲/g;
				$_ =~ s/敕/勅/g;
				$_ =~ s/鎭/鎮/g;
				$_ =~ s/塚/塚/g;
				$_ =~ s/禎/禎/g;
				$_ =~ s/遞/逓/g;
				$_ =~ s/鐵/鉄/g;
				$_ =~ s/點/点/g;
				$_ =~ s/轉/転/g;
				$_ =~ s/傳/伝/g;
				$_ =~ s/都/都/g;
				$_ =~ s/當/当/g;
				$_ =~ s/黨/党/g;
				$_ =~ s/盜/盗/g;
				$_ =~ s/稻/稲/g;
				$_ =~ s/鬪/闘/g;
				$_ =~ s/鬭/闘/g;
				$_ =~ s/德/徳/g;
				$_ =~ s/獨/独/g;
				$_ =~ s/讀/読/g;
				$_ =~ s/突/突/g;
				$_ =~ s/屆/届/g;
				$_ =~ s/內/内/g;
				$_ =~ s/難/難/g;
				$_ =~ s/貳/弐/g;
				$_ =~ s/惱/悩/g;
				$_ =~ s/腦/脳/g;
				$_ =~ s/霸/覇/g;
				$_ =~ s/拜/拝/g;
				$_ =~ s/廢/廃/g;
				$_ =~ s/賣/売/g;
				$_ =~ s/梅/梅/g;
				$_ =~ s/麥/麦/g;
				$_ =~ s/發/発/g;
				$_ =~ s/髮/髪/g;
				$_ =~ s/拔/抜/g;
				$_ =~ s/飯/飯/g;
				$_ =~ s/繁/繁/g;
				$_ =~ s/晚/晩/g;
				$_ =~ s/蠻/蛮/g;
				$_ =~ s/卑/卑/g;
				$_ =~ s/祕/秘/g;
				$_ =~ s/碑/碑/g;
				$_ =~ s/姬/姫/g;
				$_ =~ s/濱/浜/g;
				$_ =~ s/賓/賓/g;
				$_ =~ s/頻/頻/g;
				$_ =~ s/敏/敏/g;
				$_ =~ s/甁/瓶/g;
				$_ =~ s/侮/侮/g;
				$_ =~ s/福/福/g;
				$_ =~ s/拂/払/g;
				$_ =~ s/倂/併/g;
				$_ =~ s/竝/並/g;
				$_ =~ s/塀/塀/g;
				$_ =~ s/餠/餅/g;
				$_ =~ s/邊/辺/g;
				$_ =~ s/變/変/g;
				$_ =~ s/辯/弁/g;
				$_ =~ s/辨/弁/g;
				$_ =~ s/瓣/弁/g;
				$_ =~ s/勉/勉/g;
				$_ =~ s/步/歩/g;
				$_ =~ s/舖/舗/g;
				$_ =~ s/寶/宝/g;
				$_ =~ s/豐/豊/g;
				$_ =~ s/襃/褒/g;
				$_ =~ s/墨/墨/g;
				$_ =~ s/沒/没/g;
				$_ =~ s/飜/翻/g;
				$_ =~ s/槇/槙/g;
				$_ =~ s/每/毎/g;
				$_ =~ s/滿/満/g;
				$_ =~ s/免/免/g;
				$_ =~ s/麵/麺/g;
				$_ =~ s/默/黙/g;
				$_ =~ s/彌/弥/g;
				$_ =~ s/譯/訳/g;
				$_ =~ s/藥/薬/g;
				$_ =~ s/祐/祐/g;
				$_ =~ s/與/与/g;
				$_ =~ s/豫/予/g;
				$_ =~ s/餘/余/g;
				$_ =~ s/譽/誉/g;
				$_ =~ s/搖/揺/g;
				$_ =~ s/樣/様/g;
				$_ =~ s/謠/謡/g;
				$_ =~ s/遙/遥/g;
				$_ =~ s/瑤/瑶/g;
				$_ =~ s/來/来/g;
				$_ =~ s/賴/頼/g;
				$_ =~ s/亂/乱/g;
				$_ =~ s/覽/覧/g;
				$_ =~ s/欄/欄/g;
				$_ =~ s/隆/隆/g;
				$_ =~ s/旅/旅/g;
				$_ =~ s/虜/虜/g;
				$_ =~ s/兩/両/g;
				$_ =~ s/獵/猟/g;
				$_ =~ s/綠/緑/g;
				$_ =~ s/鄰/隣/g;
				$_ =~ s/淚/涙/g;
				$_ =~ s/壘/塁/g;
				$_ =~ s/類/類/g;
				$_ =~ s/禮/礼/g;
				$_ =~ s/勵/励/g;
				$_ =~ s/戾/戻/g;
				$_ =~ s/靈/霊/g;
				$_ =~ s/隸/隷/g;
				$_ =~ s/齡/齢/g;
				$_ =~ s/曆/暦/g;
				$_ =~ s/歷/歴/g;
				$_ =~ s/戀/恋/g;
				$_ =~ s/廉/廉/g;
				$_ =~ s/練/練/g;
				$_ =~ s/鍊/錬/g;
				$_ =~ s/爐/炉/g;
				$_ =~ s/勞/労/g;
				$_ =~ s/郞/郎/g;
				$_ =~ s/朗/朗/g;
				$_ =~ s/廊/廊/g;
				$_ =~ s/樓/楼/g;
				$_ =~ s/祿/禄/g;
				$_ =~ s/錄/録/g;
				$_ =~ s/灣/湾/g;
				
				print OUT $_;
			}
			close(OUT);
			close(IN);
#			unlink($file);
#			rename($file,$file . ".org");
#			rename("tmp.txt",$file);
			rename("tmp.txt", "kanji_shin_" . $file);

		}
	}



sub error{
	($sec, $min,$hour, $mday, $mon, $year, $wday) = localtime;
	$mon++;
	$year += 1900;
		open(OUT, "> error.log");
		print OUT "$_[0]\n";
		print OUT "$year/$mon/$mday  $hour:$min \n";
		close (OUT);
	
	exit(0);
	
}